Sandbox vectors

Let’s define some vectors which can be used for demonstrations:

manyNumbers <- sample( 1:1000, 20 )
manyNumbers
 [1]  90 681 238 116 548 505 653  39 134 637 170 374 369 957 240 356 839  96  60 111
manyNumbersWithNA <- sample( c( NA, NA, NA, manyNumbers ) )
manyNumbersWithNA
 [1]  NA  NA 134 505  NA  39 240  96  90 111 957 839 116 170 356  60 238 681 369 653 374 548 637
duplicatedNumbers <- sample( 1:5, 10, replace = TRUE )
duplicatedNumbers
 [1] 3 5 1 5 3 5 1 5 1 5
letters
 [1] "a" "b" "c" "d" "e" "f" "g" "h" "i" "j" "k" "l" "m" "n" "o" "p" "q" "r" "s" "t" "u" "v" "w" "x" "y" "z"
LETTERS
 [1] "A" "B" "C" "D" "E" "F" "G" "H" "I" "J" "K" "L" "M" "N" "O" "P" "Q" "R" "S" "T" "U" "V" "W" "X" "Y" "Z"
mixedLetters <- c( sample( letters, 5 ), sample( LETTERS, 5 ) )
mixedLetters
 [1] "j" "v" "l" "i" "m" "Z" "S" "A" "N" "C"

Are all/any elements TRUE

all( manyNumbers <= 1000 )
[1] TRUE
all( manyNumbers <= 500 )
[1] FALSE
any( manyNumbers > 1000 )
[1] FALSE
any( manyNumbers > 500 )
[1] TRUE
all( !is.na( manyNumbers ) )
[1] TRUE
any( is.na( manyNumbers ) )
[1] FALSE

Which elements are TRUE

Input: logical vector Output: vector of numbers (positions)

which( manyNumbers > 900 )
[1] 14
which( manyNumbersWithNA > 900 )
[1] 11
which( is.na( manyNumbersWithNA ) )
[1] 1 2 5

Filtering vector elements

manyNumbers[ manyNumbers > 900 ] # indexing by logical vector
[1] 957
manyNumbers[ which( manyNumbers > 900 ) ] # indexing by positions
[1] 957
somePositions <- which( manyNumbers > 900 )
manyNumbers[ somePositions ]
[1] 957

Are some elements among other elements

"A" %in% LETTERS
[1] TRUE
c( "X", "Y", "Z" ) %in% LETTERS
[1] TRUE TRUE TRUE
all( c( "X", "Y", "Z" ) %in% LETTERS )
[1] TRUE
all( mixedLetters %in% LETTERS )
[1] FALSE
any( mixedLetters %in% LETTERS )
[1] TRUE
mixedLetters[ mixedLetters %in% LETTERS ]
[1] "Z" "S" "A" "N" "C"
mixedLetters[ !( mixedLetters %in% LETTERS ) ]
[1] "j" "v" "l" "i" "m"
manyNumbers %in% 300:600
 [1] FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE FALSE FALSE FALSE  TRUE  TRUE FALSE FALSE  TRUE FALSE FALSE
[19] FALSE FALSE
which( manyNumbers %in% 300:600 )
[1]  5  6 12 13 16
sum( manyNumbers %in% 300:600 )
[1] 5

Pick one of two (three) depending on condition

if_else( manyNumbersWithNA >= 500, "large", "small" )
 [1] NA      NA      "small" "large" NA      "small" "small" "small" "small" "small" "large" "large" "small" "small"
[15] "small" "small" "small" "large" "small" "large" "small" "large" "large"
if_else( manyNumbersWithNA >= 500, "large", "small", "UNKNOWN" )
 [1] "UNKNOWN" "UNKNOWN" "small"   "large"   "UNKNOWN" "small"   "small"   "small"   "small"   "small"   "large"  
[12] "large"   "small"   "small"   "small"   "small"   "small"   "large"   "small"   "large"   "small"   "large"  
[23] "large"  
# here integer 0L is needed instead of real 0.0 
# manyNumbersWithNA contains integer numbers and the method complains
if_else( manyNumbersWithNA >= 500, manyNumbersWithNA, 0L ) 
 [1]  NA  NA   0 505  NA   0   0   0   0   0 957 839   0   0   0   0   0 681   0 653   0 548 637

Duplicates and unique elements

unique( duplicatedNumbers )
[1] 3 5 1
unique( c( NA, duplicatedNumbers, NA ) )
[1] NA  3  5  1
duplicated( duplicatedNumbers )
 [1] FALSE FALSE FALSE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE  TRUE

Positions of max/min elements

which.max( manyNumbersWithNA )
[1] 11
manyNumbersWithNA[ which.max( manyNumbersWithNA ) ]
[1] 957
which.min( manyNumbersWithNA )
[1] 6
manyNumbersWithNA[ which.min( manyNumbersWithNA ) ]
[1] 39
range( manyNumbersWithNA, na.rm = TRUE )
[1]  39 957

Sorting/ordering of vectors

manyNumbersWithNA
 [1]  NA  NA 134 505  NA  39 240  96  90 111 957 839 116 170 356  60 238 681 369 653 374 548 637
sort( manyNumbersWithNA )
 [1]  39  60  90  96 111 116 134 170 238 240 356 369 374 505 548 637 653 681 839 957
sort( manyNumbersWithNA, na.last = TRUE )
 [1]  39  60  90  96 111 116 134 170 238 240 356 369 374 505 548 637 653 681 839 957  NA  NA  NA
sort( manyNumbersWithNA, na.last = TRUE, decreasing = TRUE )
 [1] 957 839 681 653 637 548 505 374 369 356 240 238 170 134 116 111  96  90  60  39  NA  NA  NA
manyNumbersWithNA[1:5]
[1]  NA  NA 134 505  NA
order( manyNumbersWithNA[1:5] )
[1] 3 4 1 2 5
rank( manyNumbersWithNA[1:5] )
[1] 3 4 1 2 5
sort( mixedLetters )
 [1] "A" "C" "i" "j" "l" "m" "N" "S" "v" "Z"

Ranking of vectors

manyDuplicates <- sample( 10:15, 10, replace = TRUE )
rank( manyDuplicates )
 [1]  2.0  5.5  8.5  2.0  7.0  8.5  5.5 10.0  4.0  2.0
rank( manyDuplicates, ties.method = "min" )
 [1]  1  5  8  1  7  8  5 10  4  1
rank( manyDuplicates, ties.method = "random" )
 [1]  3  5  8  2  7  9  6 10  4  1

Rounding numbers

v <- c( -1, -0.5, 0, 0.5, 1, rnorm( 10 ) )
v
 [1] -1.000000000 -0.500000000  0.000000000  0.500000000  1.000000000  1.457656334 -1.505883670  1.085477051
 [9] -0.738247661  1.631141894  0.495322502 -0.033199100 -0.870309233 -0.007816511  1.413983911
round( v, 0 )
 [1] -1  0  0  0  1  1 -2  1 -1  2  0  0 -1  0  1
round( v, 1 )
 [1] -1.0 -0.5  0.0  0.5  1.0  1.5 -1.5  1.1 -0.7  1.6  0.5  0.0 -0.9  0.0  1.4
round( v, 2 )
 [1] -1.00 -0.50  0.00  0.50  1.00  1.46 -1.51  1.09 -0.74  1.63  0.50 -0.03 -0.87 -0.01  1.41
floor( v )
 [1] -1 -1  0  0  1  1 -2  1 -1  1  0 -1 -1 -1  1
ceiling( v )
 [1] -1  0  0  1  1  2 -1  2  0  2  1  0  0  0  2

Naming vector elements

heights <- c( Amy = 166, Eve = 170, Bob = 177 )
heights
Amy Eve Bob 
166 170 177 
names( heights )
[1] "Amy" "Eve" "Bob"
names( heights ) <- c( "AMY", "EVE", "BOB" )
heights
AMY EVE BOB 
166 170 177 
heights[[ "EVE" ]]
[1] 170

Generating grids

expand_grid( x = c( 1:3, NA ), y = c( "a", "b" ) )
# A tibble: 8 × 2
      x y    
  <int> <chr>
1     1 a    
2     1 b    
3     2 a    
4     2 b    
5     3 a    
6     3 b    
7    NA a    
8    NA b    

Generating combinations

combn( c( "a", "b", "c", "d", "e" ), m = 2, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  "c"  "d"  
[2,] "b"  "c"  "d"  "e"  "c"  "d"  "e"  "d"  "e"  "e"  
combn( c( "a", "b", "c", "d", "e" ), m = 3, simplify = TRUE )
     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
[1,] "a"  "a"  "a"  "a"  "a"  "a"  "b"  "b"  "b"  "c"  
[2,] "b"  "b"  "b"  "c"  "c"  "d"  "c"  "c"  "d"  "d"  
[3,] "c"  "d"  "e"  "d"  "e"  "e"  "d"  "e"  "e"  "e"  


Copyright © 2022 Biomedical Data Sciences (BDS) | LUMC